List your company

Mathematical Reasoning on SVAMP 10 low-resourced languages FLORES-200

7.33Kazakh (Cyrl) ScoreDIP
2.48363.741856.2582Nov 2, 2024

Evaluation results

MethodLinks
DIPModel=Llama-3.2, English pivoting (EP)=true, Chain-of-thought (CT)=false, Dictionary Insertion Prompting=true2024.117.33484.333.672.673.334.3324.674.2
DIPModel=Llama-3.2, English pivoting (EP)=true, Chain-of-thought (CT)=true, Dictionary Insertion Prompting=true2024.1173.67123.675.334.33754.3375.83
Standard PromptingModel=Llama-3.22024.11413.67333.6732.673.3333.03
English PivotingModel=Llama-3.2, English pivoting (EP)=true2024.1142.6793.3343.333.334.673.6714.3
English Pivot ThoughtModel=Llama-3.2, English pivoting (EP)=true, Chain-of-thought (CT)=true2024.1143.67132.672.333.676.674.673.333.674.8
DIPModel=Llama-3.2, English pivoting (EP)=false, Chain-of-thought (CT)=false, Dictionary Insertion Prompting=true2024.113.3354.673.67241.673.671.3342.73
Non-insertion PromptingModel=Llama-3.22024.112.672332.671.331.673111.87